OpenAI allowed the Alignment Research Center, a nonprofit founded by its ex-employee, to assess the potential risks of GPT-4 including power-seeking behavior (Benj Edwards/Ars Technica)

OpenAI allowed the Alignment Research Center, a nonprofit founded by its ex-employee, to assess the potential risks of GPT-4 including power-seeking behavior (Benj Edwards/Ars Technica)

Benj Edwards / Ars Technica:
OpenAI allowed the Alignment Research Center, a nonprofit founded by its ex-employee, to assess the potential risks of GPT-4 including power-seeking behavior  —  “ARC’s evaluation has much lower probability of leading to an AI takeover than the deployment itself.”